Python Playwright下载PDF出现net::ERR_ABORTED错误求解决方案

错误原因分析 #

你遇到的net::ERR_ABORTED错误，是因为设置always_open_pdf_externally后，调用page.goto访问PDF链接时，浏览器会尝试调用外部程序打开PDF，导致页面导航被强制中止。

解决PDF下载错误的方法 #

方案1：移除外部打开偏好，模拟内置阅读器下载 #

删掉自定义PDF外部打开的配置，页面加载PDF后，模拟点击Chromium内置阅读器的下载按钮：

from playwright.async_api import Playwright, async_playwright
import asyncio
import os

downloads_path = os.path.join(os.getcwd(), "pwtest", "downloads")
user_dir = os.path.join(os.getcwd(), "pwtest", "user_dir")

# 用os.makedirs高效创建多级目录（替代多个try-except）
os.makedirs(downloads_path, exist_ok=True)
os.makedirs(os.path.join(user_dir, "Default"), exist_ok=True)

async def run(playwright: Playwright) -> None:
    browser = await playwright.chromium.launch_persistent_context(
        user_dir, 
        accept_downloads=True, 
        headless=False, 
        slow_mo=1000
    )
    browser.set_default_timeout(10000)
    page = await browser.new_page()

    file_name = "test_d.pdf"
    async with page.expect_download() as download_info:
        await page.goto("https://www.africau.edu/images/default/sample.pdf", timeout=5000)
        # 点击内置PDF阅读器的下载按钮（Chromium默认选择器）
        await page.click("button[aria-label='下载']")
        
        download = await download_info.value
        await download.save_as(os.path.join(downloads_path, file_name))
        print(f"文件已保存至: {os.path.join(downloads_path, file_name)}")

    await browser.close()

async def main() -> None:
    async with async_playwright() as playwright:
        await run(playwright)

asyncio.run(main())

方案2：直接发起网络请求下载（无需页面渲染） #

如果不需要渲染页面，直接用Playwright的请求API获取PDF内容，效率更高：

from playwright.async_api import Playwright, async_playwright
import asyncio
import os

downloads_path = os.path.join(os.getcwd(), "pwtest", "downloads")
os.makedirs(downloads_path, exist_ok=True)

async def run(playwright: Playwright) -> None:
    browser = await playwright.chromium.launch(headless=False)
    context = await browser.new_context()
    page = await context.new_page()

    # 发起GET请求获取PDF二进制内容
    response = await page.request.get("https://www.africau.edu/images/default/sample.pdf")
    pdf_content = await response.body()

    # 写入本地文件
    file_path = os.path.join(downloads_path, "test_d.pdf")
    with open(file_path, "wb") as f:
        f.write(pdf_content)
    print(f"文件已保存至: {file_path}")

    await browser.close()

async def main() -> None:
    async with async_playwright() as playwright:
        await run(playwright)

asyncio.run(main())

拦截Blob传输的方法 #

使用page.route拦截目标请求，获取响应的Blob数据，可直接保存或处理：

from playwright.async_api import Playwright, async_playwright
import asyncio
import os

downloads_path = os.path.join(os.getcwd(), "pwtest", "downloads")
os.makedirs(downloads_path, exist_ok=True)

async def run(playwright: Playwright) -> None:
    browser = await playwright.chromium.launch(headless=False)
    context = await browser.new_context()
    page = await context.new_page()

    # 定义拦截处理逻辑
    async def intercept_blob(route):
        # 继续请求获取原始响应
        response = await route.fetch()
        # 获取Blob二进制内容
        blob_content = await response.body()
        # 保存拦截到的内容
        with open(os.path.join(downloads_path, "intercepted_blob.pdf"), "wb") as f:
            f.write(blob_content)
        print("已拦截并保存Blob内容")
        # 让页面继续加载原始响应
        await route.fulfill(response=response)

    # 匹配所有PDF格式的请求（可根据需求修改匹配规则）
    await page.route("**/*.pdf", intercept_blob)

    # 访问页面触发请求
    await page.goto("https://www.africau.edu/images/default/sample.pdf")

    await browser.close()

async def main() -> None:
    async with async_playwright() as playwright:
        await run(playwright)

asyncio.run(main())

内容的提问来源于stack exchange，提问作者NanoNerd